Getting Started with pandas

import pandas as pd

from pandas import Series, DataFrame

import numpy as np

Introduction to pandas Data Structures

Series

obj = pd.Series([4, 7, -5, 3])

obj

0 4

1 7

2 -5

3 3

dtype: int64

print(obj.values)

obj.index  # like range(4)

[ 4 7 -5 3]

RangeIndex(start=0, stop=4, step=1)

obj2 = pd.Series([4, 7, -5, 3], index=['d', 'b', 'a', 'c'])

print(obj2)

obj2.index

d 4

b 7

a -5

c 3

dtype: int64

Index(['d', 'b', 'a', 'c'], dtype='object')

obj2['a']

obj2['d'] = 6

obj2[['c', 'a', 'd']]

c 3

a -5

d 6

dtype: int64
obj2[obj2 > 0]

obj2 * 2

np.exp(obj2)

d 403.428793

b 1096.633158

a 0.006738

c 20.085537

dtype: float64

print('b' in obj2)

print('e' in obj2)

True

False

sdata = {'Ohio': 35000, 'Texas': 71000, 'Oregon': 16000, 'Utah': 5000}

obj3 = pd.Series(sdata)

obj3

Ohio 35000

Texas 71000

Oregon 16000

Utah 5000

dtype: int64

states = ['California', 'Ohio', 'Oregon', 'Texas']

obj4 = pd.Series(sdata, index=states)

obj4

California NaN

Ohio 35000.0

Oregon 16000.0

Texas 71000.0

dtype: float64

pd.isnull(obj4)

pd.notnull(obj4)

California False

Ohio True

Oregon True

Texas True

dtype: bool

obj4.isnull()

California True

Ohio False

Oregon False

Texas False

dtype: bool
print(obj3)

print(obj4)

print(obj3 + obj4)

Ohio 35000

Texas 71000

Oregon 16000

Utah 5000

dtype: int64

California NaN

Ohio 35000.0

Oregon 16000.0

Texas 71000.0

dtype: float64

California NaN

Ohio 70000.0

Oregon 32000.0

Texas 142000.0

Utah NaN

dtype: float64

obj4.name = 'population'

obj4.index.name = 'state'

obj4

state

California NaN

Ohio 35000.0

Oregon 16000.0

Texas 71000.0

Name: population, dtype: float64

print(obj)

obj.index = ['Bob', 'Steve', 'Jeff', 'Ryan']

print(obj)

0 4

1 7

2 -5

3 3

dtype: int64

Bob 4

Steve 7

Jeff -5

Ryan 3

dtype: int64

DataFrame

data = {'state': ['Ohio', 'Ohio', 'Ohio', 'Nevada', 'Nevada', 'Nevada'],
        'year': [2000, 2001, 2002, 2001, 2002, 2003],
        'pop': [1.5, 1.7, 3.6, 2.4, 2.9, 3.2]}
frame = pd.DataFrame(data)
frame

state year pop

0 Ohio 2000 1.5

1 Ohio 2001 1.7

2 Ohio 2002 3.6

3 Nevada 2001 2.4

4 Nevada 2002 2.9

5 Nevada 2003 3.2

frame.head()

state year pop

0 Ohio 2000 1.5

1 Ohio 2001 1.7

2 Ohio 2002 3.6

3 Nevada 2001 2.4

4 Nevada 2002 2.9

pd.DataFrame(data, columns=['year', 'state', 'pop'])

year state pop

0 2000 Ohio 1.5

1 2001 Ohio 1.7

2 2002 Ohio 3.6

3 2001 Nevada 2.4

4 2002 Nevada 2.9

5 2003 Nevada 3.2

frame2 = pd.DataFrame(data, columns=['year', 'state', 'pop', 'debt'],

                      index=['one', 'two', 'three', 'four',

                             'five', 'six'])

print(frame2)

print(frame2.columns)

year state pop debt

one 2000 Ohio 1.5 NaN

two 2001 Ohio 1.7 NaN

 three 2002 Ohio 3.6 NaN

four 2001 Nevada 2.4 NaN

five 2002 Nevada 2.9 NaN

six 2003 Nevada 3.2 NaN

Index(['year', 'state', 'pop', 'debt'], dtype='object')

frame2['state']

frame2.year

one 2000

two 2001

three 2002

four 2001

five 2002

six 2003

Name: year, dtype: int64

frame2.loc['three']

year 2002

state Ohio

pop 3.6

debt NaN

Name: three, dtype: object

frame2['debt'] = 16.5

print(frame2)

frame2['debt'] = np.arange(6.)

print(frame2)

year state pop debt

one 2000 Ohio 1.5 16.5

two 2001 Ohio 1.7 16.5

three 2002 Ohio 3.6 16.5

four 2001 Nevada 2.4 16.5

five 2002 Nevada 2.9 16.5

six 2003 Nevada 3.2 16.5

year state pop debt

one 2000 Ohio 1.5 0.0

two 2001 Ohio 1.7 1.0

three 2002 Ohio 3.6 2.0

four 2001 Nevada 2.4 3.0

five 2002 Nevada 2.9 4.0

six 2003 Nevada 3.2 5.0

val = pd.Series([-1.2, -1.5, -1.7], index=['two', 'four', 'five'])

frame2['debt'] = val

frame2

 year state pop debt

one 2000 Ohio 1.5 NaN

two 2001 Ohio 1.7 -1.2

three 2002 Ohio 3.6 NaN

frame2['eastern'] = frame2.state == 'Ohio'

four 2001 Nevada 2.4 -1.5

five 2002 Nevada 2.9 -1.7

six year
2003 state
Nevada pop
3.2 debt
NaN eastern

one 2000 Ohio 1.5 NaN True

two 2001 Ohio 1.7 -1.2 True

three 2002 Ohio 3.6 NaN True

four 2001 Nevada 2.4 -1.5 False

five 2002 Nevada 2.9 -1.7 False

six 2003 Nevada 3.2 NaN False

del frame2['eastern']

frame2.columns

Index(['year', 'state', 'pop', 'debt'], dtype='object')

pop = {'Nevada': {2001: 2.4, 2002: 2.9},

       'Ohio': {2000: 1.5, 2001: 1.7, 2002: 3.6}}

frame3 = pd.DataFrame(pop)

frame3

Nevada Ohio

2001 2.4 1.7

2002 2.9 3.6

2000 NaN 1.5

frame3.T

2001 2002 2000

Nevada 2.4 2.9 NaN

Ohio 1.7 3.6 1.5

pd.DataFrame(pop, index=[2001, 2002, 2003])

 Nevada Ohio

2001 2.4 1.7

2002 2.9 3.6

2003 NaN NaN

pdata = {'Ohio': frame3['Ohio'][:-1],

         'Nevada': frame3['Nevada'][:2]}

pd.DataFrame(pdata)

Ohio Nevada

2001 1.7 2.4

2002 3.6 2.9

frame3.index.name = 'year'; frame3.columns.name = 'state'

frame3

state Nevada Ohio

year

2001 2.4 1.7

2002 2.9 3.6

2000 NaN 1.5

frame3.values

array([[2.4, 1.7],

[2.9, 3.6],

[nan, 1.5]])

frame2.values

array([[2000, 'Ohio', 1.5, nan],

[2001, 'Ohio', 1.7, -1.2],

[2001, 'Nevada', 2.4, -1.5],

[2002, 'Nevada', 2.9, -1.7],

[2003, 'Nevada', 3.2, nan]], dtype=object)

Index Objects

obj = pd.Series(range(3), index=['a', 'b', 'c'])

index = obj.index

print(index)

print(index[1:])

 Index(['a', 'b', 'c'], dtype='object')

Index(['b', 'c'], dtype='object')

index[1] = 'd' # TypeError

labels = pd.Index(np.arange(3))

print(labels)

obj2 = pd.Series([1.5, -2.5, 0], index=labels)

print(obj2)

obj2.index is labels

Int64Index([0, 1, 2], dtype='int64')

0 1.5

1 -2.5

2 0.0

dtype: float64

True

frame3

frame3.columns

'Ohio' in frame3.columns

2003 in frame3.index

False

dup_labels = pd.Index(['foo', 'foo', 'bar', 'bar'])

dup_labels

Index(['foo', 'foo', 'bar', 'bar'], dtype='object')

Essential Functionality

Reindexing

obj = pd.Series([4.5, 7.2, -5.3, 3.6], index=['d', 'b', 'a', 'c'])
obj

d 4.5

b 7.2

a -5.3

c 3.6

dtype: float64

obj2 = obj.reindex(['a', 'b', 'c', 'd', 'e'])
obj2

a -5.3

 b 7.2

c 3.6

d 4.5

e NaN

dtype: float64

obj3 = pd.Series(['blue', 'purple', 'yellow'], index=[0, 2, 4])
print(obj3)
obj3.reindex(range(6), method='ffill')

0 blue

2 purple

4 yellow

dtype: object

0 blue

1 blue

2 purple

3 purple

4 yellow

5 yellow

dtype: object

frame = pd.DataFrame(np.arange(9).reshape((3, 3)),
                     index=['a', 'c', 'd'],
                     columns=['Ohio', 'Texas', 'California'])
print(frame)
frame2 = frame.reindex(['a', 'b', 'c', 'd'])
print(frame2)

Ohio Texas California

a 0 1 2

c 3 4 5

d 6 7 8

Ohio Texas California

a 0.0 1.0 2.0

b NaN NaN NaN

c 3.0 4.0 5.0

d 6.0 7.0 8.0

states = ['Texas', 'Utah', 'California']

frame.reindex(columns=states)

Texas Utah California

a 1 NaN 2

c 4 NaN 5

d 7 NaN 8

Dropping Entries from an Axis

“axis 0” represents rows and “axis 1” represents columns.

print(obj)

new_obj = obj.drop('c')
print(new_obj)

print(obj.drop(['d', 'c']))

a 0.0

b 1.0

c 2.0

d 3.0

e 4.0

dtype: float64

a 0.0

b 1.0

d 3.0

e 4.0

dtype: float64

a 0.0

b 1.0

e 4.0

dtype: float64

data = pd.DataFrame(np.arange(16).reshape((4, 4)),

                    index=['Ohio', 'Colorado', 'Utah', 'New York'],

                    columns=['one', 'two', 'three', 'four'])

data

one two three four

Ohio 0 1 2 3

Colorado 4 5 6 7

Utah 8 9 10 11

New York 12 13 14 15

data.drop(['Colorado', 'Ohio'])

one two three four

Utah 8 9 10 11

New York 12 13 14 15

print(data.drop('two', axis=1))

data.drop(['two', 'four'], axis='columns')

 one three four

Ohio 0 2 3

Colorado 4 6 7

Utah 8 10 11

New York 12 14 15

one three

Ohio 0 2

Colorado 4 6
obj.drop('c', inplace=True)

obj
Utah 8 10

aNew 0.0

York 12 14
b 1.0

d 3.0

e 4.0

dtype: float64

Indexing, Selection, and Filtering

obj = pd.Series(np.arange(4.), index=['a', 'b', 'c', 'd'])

print(obj)

print(obj['b'])

print(obj[1])

print(obj[2:4])

print(obj[['b', 'a', 'd']])

print(obj[[1, 3]])

print(obj[obj < 2])

a 0.0

b 1.0

c 2.0

d 3.0

dtype: float64

1.0

1.0

c 2.0

d 3.0

dtype: float64

b 1.0

a 0.0

d 3.0

dtype: float64

b 1.0

d 3.0

dtype: float64

a 0.0

b 1.0

dtype: float64

print(obj['b':'c'])

b 1.0

c 2.0

 dtype: float64

obj['b':'c'] = 5

obj

a 0.0

b 5.0

c 5.0

d 3.0

dtype: float64

data = pd.DataFrame(np.arange(16).reshape((4, 4)),
                    index=['Ohio', 'Colorado', 'Utah', 'New York'],
                    columns=['one', 'two', 'three', 'four'])
print(data)
print(data['two'])
print(data[['three', 'one']])

one two three four

Ohio 0 1 2 3

Colorado 4 5 6 7

Utah 8 9 10 11

New York 12 13 14 15

Ohio 1

Colorado 5

Utah 9

New York 13

Name: two, dtype: int64

three one

Ohio 2 0

Colorado 6 4

Utah 10 8

New York 14 12

data[:2]
data[data['three'] > 5]

one two three four

Colorado 4 5 6 7

Utah 8 9 10 11

New York 12 13 14 15

data < 5
data[data < 5] = 0
data
 one two three four

Ohio 0 0 0 0

Selection with loc0and5iloc

Utah 8 9 10 11
data.loc['Colorado', ['two', 'three']]
New York 12 13 14 15

two 5

three 6

Name: Colorado, dtype: int64

print(data.iloc[2, [3, 0, 1]])

print(data.iloc[2])

print(data.iloc[[1, 2], [3, 0, 1]])

four 11

one 8

two 9

Name: Utah, dtype: int64

one 8

two 9

three 10

four 11

Name: Utah, dtype: int64

four one two

Colorado 7 0 5

Utah 11 8 9

print(data.loc[:'Utah', 'two'])

print(data.iloc[:, :3][data.three > 5])

Ohio 0

Colorado 5

Utah 9

Name: two, dtype: int64

one two three

Colorado 0 5 6

Utah 8 9 10

New York 12 13 14

Integer Indexes

ser = pd.Series(np.arange(3.))
ser
ser[-1]

ser = pd.Series(np.arange(3.))

ser

0 0.0

1 1.0

 2 2.0

dtype: float64

ser2 = pd.Series(np.arange(3.), index=['a', 'b', 'c'])

ser2[-1]

2.0

print(ser[:1])

print(ser.loc[:1])

print(ser.iloc[:1])

0 0.0

dtype: float64

0 0.0

1 1.0

dtype: float64

0 0.0

dtype: float64

Arithmetic and Data Alignment

s1 = pd.Series([7.3, -2.5, 3.4, 1.5], index=['a', 'c', 'd', 'e'])
s2 = pd.Series([-2.1, 3.6, -1.5, 4, 3.1],
               index=['a', 'c', 'e', 'f', 'g'])
print(s1)
print(s2)

a 7.3

c -2.5

d 3.4

e 1.5

dtype: float64

a -2.1

c 3.6

e -1.5

f 4.0

g 3.1

dtype: float64

s1 + s2

a 5.2

c 1.1

d NaN

e 0.0

f NaN

g NaN

dtype: float64

df1 = pd.DataFrame(np.arange(9.).reshape((3, 3)), columns=list('bcd'),

                   index=['Ohio', 'Texas', 'Colorado'])

df2 = pd.DataFrame(np.arange(12.).reshape((4, 3)), columns=list('bde'),

                   index=['Utah', 'Ohio', 'Texas', 'Oregon'])

print(df1)

print(df2)

b c d

Ohio 0.0 1.0 2.0

Texas 3.0 4.0 5.0

Colorado 6.0 7.0 8.0

b d e

Utah 0.0 1.0 2.0

Ohio 3.0 4.0 5.0

Texas 6.0 7.0 8.0

Oregon 9.0 10.0 11.0

df1 + df2

b c d e

Colorado NaN NaN NaN NaN

Ohio 3.0 NaN 6.0 NaN

Oregon NaN NaN NaN NaN

Texas 9.0 NaN 12.0 NaN

Utah NaN NaN NaN NaN

df1 = pd.DataFrame({'A': [1, 2]})

df2 = pd.DataFrame({'B': [3, 4]})

print(df1)

print(df2)

print(df1 - df2)

0 1

1 2

0 3

1 4

A B

0 NaN NaN

1 NaN NaN

Arithmetic methods with fill values

df1 = pd.DataFrame(np.arange(12.).reshape((3, 4)),

                   columns=list('abcd'))

df2 = pd.DataFrame(np.arange(20.).reshape((4, 5)),

                   columns=list('abcde'))

df2.loc[1, 'b'] = np.nan

print(df1)

print(df2)

 a b c d

0 0.0 1.0 2.0 3.0

1 4.0 5.0 6.0 7.0

2 8.0 9.0 10.0 11.0

a b c d e

0 0.0 1.0 2.0 3.0 4.0

1 5.0 NaN 7.0 8.0 9.0

2 10.0 11.0 12.0 13.0 14.0

3 15.0 16.0 17.0 18.0 19.0

df1 + df2

a b c d e

0 0.0 2.0 4.0 6.0 NaN

1 9.0 NaN 13.0 15.0 NaN

2 18.0 20.0 22.0 24.0 NaN

3 NaN NaN NaN NaN NaN

df1.add(df2, fill_value=0)

a b c d e

0 0.0 2.0 4.0 6.0 4.0

1 9.0 5.0 13.0 15.0 9.0

2 18.0 20.0 22.0 24.0 14.0

3 15.0 16.0 17.0 18.0 19.0

print(1 / df1)

print(df1.rdiv(1))

a b c d

0 inf 1.000000 0.500000 0.333333

1 0.250 0.200000 0.166667 0.142857

2 0.125 0.111111 0.100000 0.090909

a b c d

0 inf 1.000000 0.500000 0.333333

1 0.250 0.200000 0.166667 0.142857

2 0.125 0.111111 0.100000 0.090909

df1.reindex(columns=df2.columns, fill_value=0)

 a b c d e
Operations
0 0.0 between
1.0 2.0 DataFrame
3.0 0 and Series
1 4.0 5.0 6.0 7.0 0
arr = np.arange(12.).reshape((3, 4))
2 8.0 9.0 10.0 11.0 0
print(arr)
print(arr[0])
print(arr - arr[0])

[[ 0. 1. 2. 3.]

[ 4. 5. 6. 7.]

[ 8. 9. 10. 11.]]

[0. 1. 2. 3.]

[[0. 0. 0. 0.]

[4. 4. 4. 4.]

[8. 8. 8. 8.]]

frame = pd.DataFrame(np.arange(12.).reshape((4, 3)),
                     columns=list('bde'),
                     index=['Utah', 'Ohio', 'Texas', 'Oregon'])
series = frame.iloc[0]
print(frame)
print(series)

b d e

Utah 0.0 1.0 2.0

Ohio 3.0 4.0 5.0

Texas 6.0 7.0 8.0

Oregon 9.0 10.0 11.0

b 0.0

d 1.0

e 2.0

Name: Utah, dtype: float64

frame - series

b d e

Utah 0.0 0.0 0.0

Ohio 3.0 3.0 3.0

Texas 6.0 6.0 6.0

Oregon 9.0 9.0 9.0

series2 = pd.Series(range(3), index=['b', 'e', 'f'])

frame + series2

 b d e f

Utah 0.0 NaN 3.0 NaN

Ohio 3.0 NaN 6.0 NaN

Texas 6.0 NaN

Oregon 9.0 NaN 12.0 NaN

b d e

Utah 0.0 1.0 2.0

Ohio 3.0 4.0 5.0

Texas 6.0 7.0 8.0

Oregon 9.0 10.0 11.0

Utah 1.0

Ohio 4.0

Texas 7.0

Oregon 10.0

Name: d, dtype: float64

b d e

Utah -1.0 0.0 1.0

Ohio -1.0 0.0 1.0

Texas -1.0 0.0 1.0

Oregon -1.0 0.0 1.0

Function Application and Mapping

frame = pd.DataFrame(np.random.randn(4, 3), columns=list('bde'),

                     index=['Utah', 'Ohio', 'Texas', 'Oregon'])

frame

np.abs(frame)

b d e

Utah 0.126328 1.202220 0.611578

Ohio 0.516871 0.583783 0.263127

Texas 1.371181 1.432754 3.784665

Oregon 1.394321 0.570987 2.535797

f = lambda x: x.max() - x.min()

frame.apply(f)

b 1.911192

d 0.861766

e 6.320462

dtype: float64

frame.apply(f, axis='columns')

Utah 1.328548

 Ohio 1.100655

Texas 2.413484

Oregon 3.930118

dtype: float64

def f(x):

    return pd.Series([x.min(), x.max()], index=['min', 'max'])

frame.apply(f)

b d e

min -0.516871 0.570987 -2.535797

max 1.394321 1.432754 3.784665

format = lambda x: '%.2f' % x

frame.applymap(format)

b d e

Utah -0.13 1.20 0.61

Ohio -0.52 0.58 -0.26

Texas 1.37 1.43 3.78

Oregon 1.39 0.57 -2.54

frame['e'].map(format)

Utah 0.61

Ohio -0.26

Texas 3.78

Oregon -2.54

Name: e, dtype: object

Sorting and Ranking

obj = pd.Series(range(4), index=['d', 'a', 'b', 'c'])

obj.sort_index()

a 1

b 2

c 3

d 0

dtype: int64

frame = pd.DataFrame(np.arange(8).reshape((2, 4)),

                     index=['three', 'one'],

                     columns=['d', 'a', 'b', 'c'])

print(frame.sort_index())

print(frame.sort_index(axis=1))

 d a b c

one 4 5 6 7

three 0 1 2 3

a b c d

three 1 2 3 0

one 5 6 7 4

frame.sort_index(axis=1, ascending=False)

d c b a

three 0 3 2 1

one 4 7 6 5

obj = pd.Series([4, 7, -3, 2])

obj.sort_values()

2 -3

3 2

0 4

1 7

dtype: int64

obj = pd.Series([4, np.nan, 7, np.nan, -3, 2])
obj.sort_values()

4 -3.0

5 2.0

0 4.0

2 7.0

1 NaN

3 NaN

dtype: float64

frame = pd.DataFrame({'b': [4, 7, -3, 2], 'a': [0, 1, 0, 1]})

print(frame)

print(frame.sort_values(by='b'))

b a

0 4 0

1 7 1

2 -3 0

3 2 1

b a

2 -3 0

3 2 1

0 4 0

1 7 1

frame.sort_values(by=['a', 'b'])

 b a

2 -3 0

0 4 0

3 2 1

1 7 1
obj = pd.Series([7, -5, 7, 4, 2, 0, 4])

obj.rank()

0 6.5

1 1.0

2 6.5

3 4.5

4 3.0

5 2.0

6 4.5

dtype: float64

obj.rank(method='first')

0 6.0

1 1.0

2 7.0

3 4.0

4 3.0

5 2.0

6 5.0

dtype: float64

# Assign tie values the maximum rank in the group

obj.rank(ascending=False, method='max')

0 2.0

1 7.0

2 2.0

3 4.0

4 5.0

5 6.0

6 4.0

dtype: float64

frame = pd.DataFrame({'b': [4.3, 7, -3, 2], 'a': [0, 1, 0, 1],

                      'c': [-2, 5, 8, -2.5]})

print(frame)

print(frame.rank(axis='columns'))

b a c

0 4.3 0 -2.0

1 7.0 1 5.0

2 -3.0 0 8.0

3 2.0 1 -2.5

b a c

0 3.0 2.0 1.0

 1 3.0 1.0 2.0

2 1.0 2.0 3.0

3 3.0 2.0 1.0

Axis Indexes with Duplicate Labels

obj = pd.Series(range(5), index=['a', 'a', 'b', 'b', 'c'])

obj

a 0

a 1

b 2

b 3

c 4

dtype: int64

obj.index.is_unique

False

print(obj['a'])

print(obj['c'])

a 0

a 1

dtype: int64

df = pd.DataFrame(np.random.randn(4, 3), index=['a', 'a', 'b', 'b'])

print(df)

print(df.loc['b'])

0 1 2

a 0.621810 1.725561 0.408424

a -0.989344 -0.940146 1.290823

b -0.374677 -0.708747 -0.668397

b 0.736185 0.029032 -0.081611

0 1 2

b -0.374677 -0.708747 -0.668397

b 0.736185 0.029032 -0.081611

Summarizing and Computing Descriptive Statistics

df = pd.DataFrame([[1.4, np.nan], [7.1, -4.5],

                   [np.nan, np.nan], [0.75, -1.3]],

                  index=['a', 'b', 'c', 'd'],

                  columns=['one', 'two'])

df

 one two

a 1.40 NaN

b 7.10 -4.5

c NaN NaN

d 0.75 -1.3
df.sum()

one 9.25

two -5.80

dtype: float64

df.sum(axis='columns')

a 1.40

b 2.60

c 0.00

d -0.55

dtype: float64

df.mean(axis='columns', skipna=False)

a NaN

b 1.300

c NaN

d -0.275

dtype: float64

df.idxmax()

one b

two d

dtype: object

df.cumsum()

one two

a 1.40 NaN

b 8.50 -4.5

c NaN NaN

d 9.25 -5.8

df.describe()

 one two

count 3.000000 2.000000

mean 3.083333 -2.900000

std 3.493685 2.262742

min 0.750000 -4.500000

25% 1.075000 -3.700000

50% 1.400000 -2.900000

75% 4.250000 -2.100000

count 16

unique 3

top a

freq 8

dtype: object

Unique Values, Value Counts, and Membership

obj = pd.Series(['c', 'a', 'd', 'a', 'a', 'b', 'b', 'c', 'c'])

uniques = obj.unique()
uniques

array(['c', 'a', 'd', 'b'], dtype=object)

obj.value_counts()

c 3

a 3

b 2

d 1

dtype: int64

pd.value_counts(obj.values, sort=False)

c 3

a 3

d 1

b 2

dtype: int64

print(obj)

mask = obj.isin(['b', 'c'])

print(mask)

print(obj[mask])

 0 c

1 a

2 d

3 a

4 a

5 b

6 b

7 c

8 c

dtype: object

0 True

1 False

2 False

3 False

4 False

5 True

6 True

7 True

8 True

dtype: bool

0 c

5 b

6 b

7 c

8 c

dtype: object

to_match = pd.Series(['c', 'a', 'b', 'b', 'c', 'a'])

unique_vals = pd.Series(['c', 'b', 'a'])

pd.Index(unique_vals).get_indexer(to_match)

array([0, 2, 1, 1, 0, 2])

data = pd.DataFrame({'Qu1': [1, 3, 4, 3, 4],

                     'Qu2': [2, 3, 1, 2, 3],

                     'Qu3': [1, 5, 2, 4, 4]})

data

Qu1 Qu2 Qu3

0 1 2 1

1 3 3 5

2 4 1 2

3 3 2 4

4 4 3 4

result = data.apply(pd.value_counts).fillna(0)

result

 Qu1 Qu2 Qu3

1 1.0 1.0 1.0

2 0.0 2.0 1.0

3 2.0 2.0 0.0

4 2.0 0.0 2.0

5 0.0 0.0 1.0

Colab paid products

check 0s completed at 4:28 PM